Unlock instant, AI-driven research and patent intelligence for your innovation.

Image texture classification method based on contrast ratio local binary pattern

A local binary pattern, image texture technology, applied in character and pattern recognition, computer parts, instruments, etc., can solve the problem of local binary pattern only considering symbol features, low recognition rate, etc., to achieve fast texture image classification, Guaranteed classification performance and improved accuracy

Inactive Publication Date: 2018-09-21
HENAN UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a texture classification method based on the extended contrast local binary pattern, to solve the problem that only the sign feature of the local binary pattern (LBP) is considered in the texture feature extraction and the recognition rate is low

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image texture classification method based on contrast ratio local binary pattern
  • Image texture classification method based on contrast ratio local binary pattern
  • Image texture classification method based on contrast ratio local binary pattern

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] The specific process of the present invention is set forth as follows by classifying the texture images in the standard texture library Brodatz:

[0064] (1) Preprocess the texture image. The Brodatz texture database is an international general texture image database. There are 111 texture classes in total, and each texture class is a 640*640 grayscale texture image. In the process of preprocessing the texture set, in our experiments, we take the central area of ​​each image of 320*320 as the experimental image. In order to verify the rotation invariance of the method, we rotate each 320*320 grayscale texture image. We rotate each class clockwise: 0 degrees, 5 degrees, 10 degrees, 30 degrees, 45 degrees, 60 degrees, 75 degrees, 90 degrees, such as Figure 5 shown. For this texture set, we designed three data sets. We divided each rotated 320*320 grayscale texture image class into four 160*160 experimental samples, so each class corresponds to 32 160*160 Experimental ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an image texture classification method based on a contrast ratio local binary pattern. The method comprises the following steps: extracting symbol characteristics of an image;extracting contrast ratio differential energy characteristics of the image; extracting central pixel characteristics of the image; integrating the symbol characteristics, the contrast ratio differential energy characteristics and the central pixel characteristics of the image, acquiring symbol energy central pixel histogram characteristics of the image, and establishing histograms; classifying thehistograms by using a nearest neighbor classifier on the basis of chi-square distances. The method has the beneficial effect that the accuracy rate of characteristic extraction and classification canbe increased.

Description

technical field [0001] The invention relates to the technical field of pattern recognition and image processing, in particular to an image texture classification method based on contrast local binary patterns. Background technique [0002] With the rapid development of computer technology and the development of related fields such as computer vision and pattern recognition, image processing technology has become more and more mature. For example, Google and Baidu have launched photo search services. Baidu established Baidu Data Visualization Lab to create a deep learning platform. We can scan pictures for Baidu image recognition; the powerful view system in Taobao makes it possible to almost accurately search for the same or similar products by inputting a picture of a product. Such as face recognition in iphoneX now. The above-mentioned technologies all find accurate picture information by extracting features from the image. [0003] Texture plays an important role in p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/46G06K9/62
CPCG06V10/507G06F18/24147
Inventor 董永生司马洁梁灵飞郑林涛杨春蕾王田玉普杰信
Owner HENAN UNIV OF SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com